知识卡片
正半定二次型可近似解线性方程组
对对称正半定A,f(x)=½xᵀAx−bᵀx的梯度为Ax−b。
只有Ax=b可解(b在A的值域内)时,f才有极小点且极小点满足该方程;合适步长的梯度下降可逼近解。
若A=0且b≠0,目标无下界,不能称为近似求解。
这张卡片看不懂?
这张卡片的反馈已满 10 条,暂时无法继续提交。
已有反馈 · 0 / 10 条
还没有人提交反馈。
在整书笔记中的位置
原书出处 · 1 处
- 第33章 机器学习算法 · 查看原书依据
We now generalize this idea to higher dimensions, where using gradient descent may actually lead to a faster algorithm. One n-dimensional analog is the function , where A is an n × n matrix. The gradient of f with respect to x is the function Ax – b. To find the value of x that minimizes f, we set the gradient of f to 0 and solve for x. Solving Ax–b = 0 for x, we obtain x = A−1b, Thus, minimizing f(x) is equivalent to solving Ax = b. If f(x) is convex, then gradient descent can approximately compute this minimum. A 1-dimensional function is convex when its second derivative is positive. The equivalent definition for a multidimensional function is that it is convex when its Hessian matrix is